<ul><li>Researchers propose GATT, a method for calculating edge attributions in self-attention message passing neural networks (MPNNs) based on the computation tree.</li><li>GATT aims to bridge the gap between the widespread usage of attention-based MPNNs (Att-GNNs) and their potential explainability.</li><li>The proposed method improves edge attribution scores, demonstrating effectiveness in model explanation, faithfulness, explanation accuracy, and case studies.</li><li>The code for GATT is available on GitHub for reference.</li></ul>

Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint

Discover more